Through analysis of Traditional CAD software modeling methods, combined with process planning requirements of intelligent virtual assembly, in the proposed semantic-based multi-level top-down model of virtual assembly. This paper proposes a semantic-based top-down model of multi-level virtual assembly.On this basis, the assembly semantic information extraction process is Focused analyzed, in the three-dimensional model data, non-geometric factors such as assorted features, assembly features, assembly engineering relations are extracted, and modeling is Established by Protégé ontology-based tool, the model is imported into the 3DVAPP(3D Virtual Assembly Process Planning) system to be verified, and Finally this paper implementated the assembly process planning applications such as intelligent parts identification, Provide a theoretical and practical basis for intelligent virtual assembly.

To improve the efficiency of Assembly Sequences Planning (ASP), a new approach based on heuristic assembly knowledge and genetic algorithm was proposed. First, Connection Graph of Assembly (CGA) was introduced, and then, assembly knowledge was described in the form of Assembly Rings, on that basis, the assembly connection graph model containing Assembly Rings was defined, and the formation of initial population algorithm was given. In addition, a function was designed to measure the feasible assembly and then the genetic algorithm fitness function was given. Finally, an example was shown to illustrate the effectiveness of the algorithm.

The traditional effective variance weighted least squares algorithms for solving CMB (Chemical Mass Balance) models have the following drawbacks: When there is collinearity among the sources or the number of species is less than the number of sources, then some negative value of contribution will appear in the results of the source apportionment or the algorithm does not converge to calculation. In this paper, a novel robust algorithm based on enhanced sampling Monte Carlo simulation and effective variance weighted least squares (ESMC-CMB) is proposed, which overcomes the above weaknesses. In the following practical instances for source apportionment, when nine species and nine sources, with no collinearity among them, are selected, EPA-CMB8.2 (U.S. Environmental Protection Agency-CMB8.2), NKCMB1.0 (NanKai University, China-CMB1.0) and ESMC-CMB can obtain similar results. When the source raise dust is added to the source profiles, or nine sources and eight species are selected, EPA-CMB8.2 and NKCMB1.0 cannot solve the model, but the proposed ESMC-CMB algorithm can achieve satisfactory results that fully verify the robustness and effectiveness of ESMC-CMB.

According to the characteristics and needs of complicated products, a method for handing assembly sequence based on improved Slope One algorithm was proposed. On the basis of that the network graph of assembly relationship was constructed, and a method for simplifying it was proposed by expressing elliptically same parts, identifying and hiding fasteners. In this paper, Slope One algorithm was initially introduced into the assembly sequence planning, and it was improved according to the problems to be resolved. In the meantime, particle swarm optimization algorithm was introduced into the feedback of the recommendation result. The method has been proved that it was not only used to obtain a good recommendation of assembly sequence but also sensitive to the individuation of designers.

Virtual Assembly (VA) is an advanced tool for assembly design. Current VA system lacks of intelligent decision support especially in assignment of assembly planning task. There are already some research to enhance the perception ability and intelligent support of VR. However, most of them are focusing on the auto mating or moving navigation, while the study on assembly task is few. The paper analyzed the task in virtual assembly and discussed the system level task as a main topic, which indicated that ‘work-flow’ was a suitably way to implement task aware. Therefore a BDI agent model for assembly task was proposed on the bases of work-flow and the architecture of it was given. After these, the reasoning mechanism was designed to support assembly task awareness.